mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 18:09:05 -04:00
1cd7d63c7b
#10970 gave the four PredictOptions RPCs a model-identity check so a backend reached through a stale distributed route rejects the request instead of answering from whatever model it holds (#10952). Every other modality shares that exposure: the route is cached by host:port, a worker can recycle a stopped backend's port for another model's backend, and a liveness-only probe cannot tell a stale row from a valid one. Extends the same mechanism to the 21 remaining request messages that reach a backend through the router, using the pattern #10970 established rather than a parallel one: - proto: ModelIdentity on each modality request message. - controller: populated from ModelConfig.Model at the call site that also builds ModelOptions, so load-time and request-time values are equal by construction. - backends: one generic guard in pkg/grpc/server.go (27 Go backends), the method set in backend/python/common (36 Python backends), llama-cpp (AudioTranscription/Stream, Rerank, Score) and privacy-filter (TokenClassify). - reconcile already drops the stale row on IsModelMismatch; no change. TTSRequest and SoundGenerationRequest get a SEPARATE ModelIdentity field rather than reusing their existing `model`: FileStagingClient rewrites `model` to a worker-local path, so comparing it would reject valid requests in exactly the configuration this guards. AudioEncode/AudioDecode are deliberately left unguarded: the opus codec backend is loaded from a literal rather than a ModelConfig, so no value carries the equality guarantee the comparison depends on. The four bidirectional stream RPCs are out of scope; they bypass reconcile. Empty means skip on both sides, so an old controller, an old backend, and the bare request structs in tests/e2e-backends all keep working. Assisted-by: Claude Code:claude-opus-4-8 [Read] [Edit] [Bash] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
71 lines
1.9 KiB
Go
71 lines
1.9 KiB
Go
package backend
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"time"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/trace"
|
|
"github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
// Depth runs depth estimation (Depth Anything 3) on the supplied image and
|
|
// returns the full DepthResponse: per-pixel metric depth + confidence + sky,
|
|
// camera pose (extrinsics/intrinsics), an optional 3D point cloud and any
|
|
// requested exports (glb/colmap). The include_* flags and exports mirror the
|
|
// DepthRequest proto so callers can ask for less work.
|
|
func Depth(
|
|
ctx context.Context,
|
|
in *proto.DepthRequest,
|
|
loader *model.ModelLoader,
|
|
appConfig *config.ApplicationConfig,
|
|
modelConfig config.ModelConfig,
|
|
) (*proto.DepthResponse, error) {
|
|
opts := ModelOptions(modelConfig, appConfig)
|
|
depthModel, err := loader.Load(opts...)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return nil, err
|
|
}
|
|
|
|
if depthModel == nil {
|
|
return nil, fmt.Errorf("could not load depth model")
|
|
}
|
|
|
|
var startTime time.Time
|
|
if appConfig.EnableTracing {
|
|
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
|
|
startTime = time.Now()
|
|
}
|
|
|
|
// Stamped here for the same reason as in rerank.go: the caller builds the
|
|
// request without a ModelConfig, this function has the one that loaded.
|
|
in.ModelIdentity = modelConfig.Model
|
|
|
|
res, err := depthModel.Depth(ctx, in)
|
|
|
|
if appConfig.EnableTracing {
|
|
errStr := ""
|
|
if err != nil {
|
|
errStr = err.Error()
|
|
}
|
|
|
|
trace.RecordBackendTrace(trace.BackendTrace{
|
|
Timestamp: startTime,
|
|
Duration: time.Since(startTime),
|
|
Type: trace.BackendTraceDepth,
|
|
ModelName: modelConfig.Name,
|
|
Backend: modelConfig.Backend,
|
|
Summary: trace.TruncateString(in.GetSrc(), 200),
|
|
Error: errStr,
|
|
Data: map[string]any{
|
|
"exports": in.GetExports(),
|
|
},
|
|
})
|
|
}
|
|
|
|
return res, err
|
|
}
|